Concept induction, which is based on formal logical reasoning over description logics, has been used in ontology engineering in order to create ontology (TBox) axioms from the base data (ABox) graph. In this paper, we show that it can also be used to explain data differentials, for example in the context of Explainable AI (XAI), and we show that it can in fact be done in a way that is meaningful to a human observer. Our approach utilizes a large class hierarchy, curated from the Wikipedia category hierarchy, as background knowledge.
@article{arxiv.2209.13710,
title = {Towards Human-Compatible XAI: Explaining Data Differentials with Concept Induction over Background Knowledge},
author = {Cara Widmer and Md Kamruzzaman Sarker and Srikanth Nadella and Joshua Fiechter and Ion Juvina and Brandon Minnery and Pascal Hitzler and Joshua Schwartz and Michael Raymer},
journal= {arXiv preprint arXiv:2209.13710},
year = {2022}
}